gitlab-babysit-mr

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). At runtime the required workflow fetches and ingests MR pipeline/job free text produced by outsiders—specifically it pulls the failing job trace/log tail via scripts/job_log_tail.sh (used in Phase 2) and then classifies and searches using contents derived from that log.